{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:16:41Z","timestamp":1759133801680,"version":"3.37.3"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T00:00:00Z","timestamp":1568764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T00:00:00Z","timestamp":1568764800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s00371-019-01751-1","type":"journal-article","created":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T10:03:21Z","timestamp":1568801001000},"page":"1457-1471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Action matching network: open-set action recognition using spatio-temporal representation matching"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0718-9948","authenticated-orcid":false,"given":"Jongmin","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Du Yong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongsang","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moongu","family":"Jeon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,18]]},"reference":[{"key":"1751_CR1","unstructured":"Brand, M., Oliver, N., Pentland, A.: Coupled hidden Markov models for complex action recognition. In: CVPR, p. 994. IEEE (1997)"},{"issue":"8","key":"1751_CR2","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1016\/S0262-8856(03)00070-2","volume":"21","author":"F-S Chen","year":"2003","unstructured":"Chen, F.-S., Fu, C.-M., Huang, C.-L.: Hand gesture recognition using a real-time tracking method and hidden Markov models. Image Vis. Comput. 21(8), 745\u2013758 (2003)","journal-title":"Image Vis. Comput."},{"key":"1751_CR3","doi-asserted-by":"crossref","unstructured":"Suk, H.-I., Sin, B.-K., Lee, S.-W.: Recognizing hand gestures using dynamic Bayesian network. In: 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 1\u20136. IEEE (2008)","DOI":"10.1109\/AFGR.2008.4813342"},{"issue":"9","key":"1751_CR4","doi-asserted-by":"publisher","first-page":"3059","DOI":"10.1016\/j.patcog.2010.03.016","volume":"43","author":"H-I Suk","year":"2010","unstructured":"Suk, H.-I., Sin, B.-K., Lee, S.-W.: Hand gesture recognition based on dynamic Bayesian network framework. Pattern Recognit. 43(9), 3059\u20133072 (2010)","journal-title":"Pattern Recognit."},{"issue":"11","key":"1751_CR5","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"1751_CR6","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","DOI":"10.1145\/3065386"},{"key":"1751_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1751_CR8","doi-asserted-by":"crossref","unstructured":"Eitel, A., Springenberg, J.T., Spinello, L., Riedmiller, M., Burgard, W.: Multimodal deep learning for robust RGB-D object recognition. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 681\u2013687. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353446"},{"key":"1751_CR9","unstructured":"Socher, R., Huval, B., Bath, B., Manning, C.D., Ng, A.Y.: Convolutional-recursive deep learning for 3D object classification. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, NIPS\u201912, vol. 1, pp. 656\u2013664. Curran Associates Inc., USA (2012)"},{"key":"1751_CR10","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"1751_CR11","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1891\u20131898 (2014)","DOI":"10.1109\/CVPR.2014.244"},{"key":"1751_CR12","unstructured":"Sun, Y., Liang, D., Wang, X., Tang, X.: Deepid3: face recognition with very deep neural networks. arXiv preprint arXiv:1502.00873 (2015)"},{"key":"1751_CR13","doi-asserted-by":"crossref","unstructured":"Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 1 (2017)","DOI":"10.1109\/CVPR.2017.713"},{"issue":"4","key":"1751_CR14","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s00371-013-0861-x","volume":"30","author":"Z Wang","year":"2014","unstructured":"Wang, Z., Miao, Z., Wu, Q.M.J., Wan, Y., Tang, Z.: Low-resolution face recognition: a review. Vis. Comput. 30(4), 359\u2013386 (2014)","journal-title":"Vis. Comput."},{"key":"1751_CR15","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1751_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1751_CR17","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"1751_CR18","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"issue":"1","key":"1751_CR19","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s00371-014-1059-6","volume":"32","author":"Y Tang","year":"2016","unstructured":"Tang, Y., Tong, R., Tang, M., Zhang, Y.: Depth incorporating with color improves salient object detection. Vis Comput 32(1), 111\u2013121 (2016)","journal-title":"Vis Comput"},{"issue":"12","key":"1751_CR20","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder\u2013decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"1751_CR21","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2017.2712691","volume":"40","author":"B Shuai","year":"2018","unstructured":"Shuai, B., Zuo, Z., Wang, B., Wang, G.: Scene segmentation with dag-recurrent neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1480\u20131493 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1751_CR22","doi-asserted-by":"crossref","unstructured":"Kumar, P., Nagar, P., Arora, C., Gupta, A.: U-Segnet: fully convolutional neural network based automated brain tissue segmentation tool. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 3503\u20133507. IEEE (2018)","DOI":"10.1109\/ICIP.2018.8451295"},{"key":"1751_CR23","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, NIPS\u201914, vol. 1, pp. 568\u2013576 (2014)"},{"issue":"1","key":"1751_CR24","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1751_CR25","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"1751_CR26","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Yeung, D.-Y., Shi, B.E.: Human action recognition using factorized spatio-temporal convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4597\u20134605 (2015)","DOI":"10.1109\/ICCV.2015.522"},{"issue":"4","key":"1751_CR27","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1109\/THMS.2015.2504550","volume":"46","author":"P Wang","year":"2016","unstructured":"Wang, P., Li, W., Gao, Z., Zhang, J., Tang, C., Ogunbona, P.O.: Action recognition from depth maps using deep convolutional neural networks. IEEE Trans Hum Mach Syst 46(4), 498\u2013509 (2016)","journal-title":"IEEE Trans Hum Mach Syst"},{"key":"1751_CR28","doi-asserted-by":"publisher","unstructured":"Yu, J., Park, S., Lee, S., Jeon, M.: Driver drowsiness detection using condition-adaptive representation learning framework. IEEE Trans. Intell. Transp. Syst. (2018). https:\/\/doi.org\/10.1109\/TITS.2018.2883823","DOI":"10.1109\/TITS.2018.2883823"},{"key":"1751_CR29","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.patcog.2018.07.030","volume":"85","author":"Y Yang","year":"2019","unstructured":"Yang, Y., Hou, C., Lang, Y., Guan, D., Huang, D., Xu, J.: Open-set human activity recognition based on micro-doppler signatures. Pattern Recognit. 85, 60\u201369 (2019)","journal-title":"Pattern Recognit."},{"key":"1751_CR30","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"1751_CR31","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1751_CR32","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"1751_CR33","doi-asserted-by":"crossref","unstructured":"Park, S., Yu, J., Jeon, M.: Learning feature representation for face verification. In: 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/AVSS.2017.8078466"},{"key":"1751_CR34","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701\u20131708 (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"1751_CR35","unstructured":"Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol. 2 (2015)"},{"issue":"4","key":"1751_CR36","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1007\/s00371-015-1079-x","volume":"32","author":"X-N Hou","year":"2016","unstructured":"Hou, X.-N., Ding, S.-H., Ma, L.-Z., Wang, C.-J., Li, J.-L., Huang, F.-Y.: Similarity metric learning for face verification using sigmoid decision function. Vis. Comput. 32(4), 479\u2013490 (2016)","journal-title":"Vis. Comput."},{"issue":"11","key":"1751_CR37","doi-asserted-by":"publisher","first-page":"1535","DOI":"10.1007\/s00371-017-1429-y","volume":"34","author":"JY Choi","year":"2018","unstructured":"Choi, J.Y.: Spatial pyramid face feature representation and weighted dissimilarity matching for improved face recognition. Vis. Comput. 34(11), 1535\u20131549 (2018)","journal-title":"Vis. Comput."},{"issue":"11","key":"1751_CR38","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1007\/s00371-011-0659-7","volume":"28","author":"C Singh","year":"2012","unstructured":"Singh, C., Walia, E., Mittal, N.: Robust two-stage face recognition approach using global and local features. Vis. Comput. 28(11), 1085\u20131098 (2012)","journal-title":"Vis. Comput."},{"key":"1751_CR39","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, R., Xiao, T., Wang, X.: Deepreid: deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 152\u2013159 (2014)","DOI":"10.1109\/CVPR.2014.27"},{"key":"1751_CR40","doi-asserted-by":"crossref","unstructured":"Xiao, T., Li, H., Ouyang, W., Wang, X.: Learning deep feature representations with domain guided dropout for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1249\u20131258 (2016)","DOI":"10.1109\/CVPR.2016.140"},{"key":"1751_CR41","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"issue":"6","key":"1751_CR42","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2018","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1510\u20131517 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"1751_CR43","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/TCSVT.2016.2628339","volume":"28","author":"Y Hou","year":"2018","unstructured":"Hou, Y., Li, Z., Wang, P., Li, W.: Skeleton optical spectra-based action recognition using convolutional neural networks. IEEE Trans. Circuits Syst. Video Technol. 28(3), 807\u2013811 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1751_CR44","doi-asserted-by":"crossref","unstructured":"Shi, Y., Wang, Y., Zou, Y., Yuan, Q., Tian, Y., Shu, Y.: ODN: opening the deep network for open-set action recognition. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ICME.2018.8486452"},{"key":"1751_CR45","doi-asserted-by":"crossref","unstructured":"Bucilu\u01ce, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 535\u2013541. ACM (2006)","DOI":"10.1145\/1150402.1150464"},{"key":"1751_CR46","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Morariu, V.I., Davis, L.S.: Visual relationship detection with internal and external linguistic knowledge distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1974\u20131982 (2017)","DOI":"10.1109\/ICCV.2017.121"},{"key":"1751_CR47","unstructured":"Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917, pp. 742\u2013751 (2017)"},{"key":"1751_CR48","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1751_CR49","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Learning spatio-temporal features with 3D residual networks for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3154\u20133160 (2017)","DOI":"10.1109\/ICCVW.2017.373"},{"key":"1751_CR50","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, vol. 1, p. 3 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"issue":"16\u201318","key":"1751_CR51","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1016\/j.neucom.2008.04.030","volume":"71","author":"C-Y Liou","year":"2008","unstructured":"Liou, C.-Y., Huang, J.-C., Yang, W.-C.: Modeling word perception using the Elman network. Neurocomputing 71(16\u201318), 3150\u20133157 (2008)","journal-title":"Neurocomputing"},{"issue":"Dec","key":"1751_CR52","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.-A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(Dec), 3371\u20133408 (2010)","journal-title":"J. Mach. Learn. Res."},{"issue":"5786","key":"1751_CR53","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"issue":"1","key":"1751_CR54","first-page":"12","volume":"52","author":"DSC Biggs","year":"2010","unstructured":"Biggs, D.S.C.: 3D deconvolution microscopy. Curr. Protoc. Cytom. 52(1), 12\u201319 (2010)","journal-title":"Curr. Protoc. Cytom."},{"key":"1751_CR55","doi-asserted-by":"crossref","unstructured":"Hong, S., Oh, J., Lee, H., Han, B.: Learning transferrable knowledge for semantic segmentation with deep convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3204\u20133212 (2016)","DOI":"10.1109\/CVPR.2016.349"},{"key":"1751_CR56","doi-asserted-by":"crossref","unstructured":"Yu, J., Ko, D., Moon, H., Jeon, M.: Deep discriminative representation learning for face verification and person re-identification on unconstrained condition. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1658\u20131662. IEEE (2018)","DOI":"10.1109\/ICIP.2018.8451494"},{"key":"1751_CR57","unstructured":"Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report, Technical Report 07-49, University of Massachusetts, Amherst (2007)"},{"key":"1751_CR58","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., Suleyman, M., Zisserman, A.: The kinetics human action video dataset. CoRR, arXiv:abs\/1705.06950 (2017)"},{"key":"1751_CR59","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: Proceedings of the International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1751_CR60","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"issue":"3","key":"1751_CR61","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/s11263-015-0859-0","volume":"119","author":"L Wang","year":"2016","unstructured":"Wang, L., Qiao, Y., Tang, X.: MoFAP: a multi-level representation for action recognition. Int. J. Comput. Vis. 119(3), 254\u2013271 (2016)","journal-title":"Int. J. Comput. Vis."},{"issue":"2\u20133","key":"1751_CR62","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space\u2013time interest points. Int. J. Comput. Vis. 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"1751_CR63","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4305\u20134314 (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"1751_CR64","doi-asserted-by":"crossref","unstructured":"Lan, Z., Zhu, Y., Hauptmann, A.G., Newsam, S.: Deep local video feature for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1\u20137 (2017)","DOI":"10.1109\/CVPRW.2017.161"},{"key":"1751_CR65","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: Actionvlad: learning spatio-temporal aggregation for action classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 971\u2013980 (2017)","DOI":"10.1109\/CVPR.2017.337"},{"key":"1751_CR66","doi-asserted-by":"crossref","unstructured":"Wang, Y., Long, M., Wang, J., Yu, P.S.: Spatiotemporal pyramid network for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1529\u20131538 (2017)","DOI":"10.1109\/CVPR.2017.226"},{"key":"1751_CR67","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Van Gool, L.: Deep temporal linear encoding networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2329\u20132338 (2017)","DOI":"10.1109\/CVPR.2017.168"},{"issue":"12","key":"1751_CR68","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1109\/TPAMI.2017.2769085","volume":"40","author":"H Bilen","year":"2018","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A.: Action recognition with dynamic image networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2799\u20132813 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1751_CR69","doi-asserted-by":"crossref","unstructured":"Zhu, J., Zhu, Z., Zou, W.: End-to-end video-level representation learning for action recognition. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 645\u2013650. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8545710"},{"key":"1751_CR70","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-019-01751-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00371-019-01751-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-019-01751-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T23:39:13Z","timestamp":1664408353000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00371-019-01751-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,18]]},"references-count":70,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["1751"],"URL":"https:\/\/doi.org\/10.1007\/s00371-019-01751-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2019,9,18]]},"assertion":[{"value":"18 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}